Google

llm

Gemini 3.5 Flash

Gemini 3.5 Flash

Gemini 3.5 Flash

Google's fast multimodal model with a massive 1M token context window — ideal for large documents or codebases.

Google's fast multimodal model with a massive 1M token context window — ideal for large documents or codebases.

All models

chat, vision

REQUEST

llm

curl -X POST https://api.apiarium.dev/llm -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" -d '{"model":"gemini","messages":[{"role":"user","content":"Hello"}]}'

curl -X POST https://api.apiarium.dev/llm -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" -d '{"model":"gemini","messages":[{"role":"user","content":"Hello"}]}'

Context window

1M

1M

Max output

8.2K

8.2K

Credits

9.375 credits / 1K input tokens, 56.25 credits / 1K output tokens

USD equivalent

$1.50 / $9.00 per 1M tokens (input/output)

MODEL NOTES

Gemini 3.5 Flash is Google's fast multimodal model, and its standout feature is context: a 1,000,000 token window, roughly five times larger than Claude's and eight times larger than GPT-4o's. That's enough to fit an entire book, a large codebase, or hours of transcript in a single request.

If your use case involves genuinely large inputs — analyzing a full repository, summarizing a lengthy document collection, or maintaining very long conversation history — this is the model built for that, not a workaround.

For typical short-context tasks, it's not automatically the best choice; the value here is specifically the context window, not raw output quality relative to Claude or GPT-4o.

‹ Claude Sonnet 4.5

GPT Image 1 ›